papers

Publications (16)

eess.IV2024

Boosting Spatial-Spectral Masked Auto-Encoder Through Mining Redundant Spectra for HSI-SAR/LiDAR Classification

Junyan Lin, Xuepeng Jin, Feng Gao +2

Although recent masked image modeling (MIM)-based HSI-LiDAR/SAR classification methods have gradually recognized the importance of the spectral information, they have not adequatel…

cs.CV2026

Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification

Xin Jin, Jinming Liu, Yuntao Wei +6

"Compression Tells Intelligence", is supported by research in artificial intelligence, particularly concerning (multimodal) large language models (LLMs/MLLMs), where compression ef…

cs.CL2024

To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimodal Large Language Models

Junyan Lin, Haoran Chen, Dawei Zhu +1

In recent years, multimodal large language models (MLLMs) have garnered significant attention from both industry and academia. However, there is still considerable debate on constr…

cs.CV2024

Tell Codec What Worth Compressing: Semantically Disentangled Image Coding for Machine with LMMs

Jinming Liu, Yuntao Wei, Junyan Lin +5

We present a new image compression paradigm to achieve ``intelligently coding for machine'' by cleverly leveraging the common sense of Large Multimodal Models (LMMs). We are motiva…

eess.IV2025

Dynamic Cross-Modal Feature Interaction Network for Hyperspectral and LiDAR Data Classification

Junyan Lin, Feng Gap, Lin Qi +3

Hyperspectral image (HSI) and LiDAR data joint classification is a challenging task. Existing multi-source remote sensing data classification methods often rely on human-designed f…

cs.RO2026

DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning

Zili Lin, Wenyao Zhang, Yuyang Zhang +9

Demonstration augmentation is proposed for cost-efficient data acquisition, but existing methods are fundamentally limited in deformable manipulation due to two challenges: (1) the…

cs.CV2025

Multimodal Language Models See Better When They Look Shallower

Haoran Chen, Junyan Lin, Xinghao Chen +6

Multimodal large language models (MLLMs) typically extract visual features from the final layers of a pretrained Vision Transformer (ViT). This widespread deep-layer bias, however,…

cs.CV2025

Revisiting MLLM Token Technology through the Lens of Classical Visual Coding

Jinming Liu, Junyan Lin, Yuntao Wei +7

Classical visual coding and Multimodal Large Language Model (MLLM) token technology share the core objective - maximizing information fidelity while minimizing computational cost.…

eess.IV2026

Representative Spectral Correlation Network for Multi-source Remote Sensing Image Classification

Chuanzheng Gong, Feng Gao, Junyan Lin +2

Hyperspectral image (HSI) and SAR/LiDAR data offer complementary spectral and structural information for land-cover classification. However, their effective fusion remains challeng…

eess.IV2023

SS-MAE: Spatial-Spectral Masked Auto-Encoder for Multi-Source Remote Sensing Image Classification

Junyan Lin, Feng Gao, Xiaocheng Shi +2

Masked image modeling (MIM) is a highly popular and effective self-supervised learning method for image understanding. Existing MIM-based methods mostly focus on spatial feature mo…

cs.CV2026

UTPTrack: Towards Simple and Unified Token Pruning for Visual Tracking

Hao Wu, Xudong Wang, Jialiang Zhang +5

One-stream Transformer-based trackers achieve advanced performance in visual object tracking but suffer from significant computational overhead that hinders real-time deployment. W…

cs.CV2026

Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion

Jinming Liu, Yuntao Wei, Junyan Lin +5

Learned image compression methods have shown impressive performance but are often highly specialized for either human perception or specific machine vision tasks. This specializati…

cs.CV2026

Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models

Jialiang Zhang, Junlong Tong, Junyan Lin +4

Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style…

cs.CV2025

Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices

Junyan Lin, Haoran Chen, Yue Fan +5

Multimodal Large Language Models (MLLMs) have made significant advancements in recent years, with visual features playing an increasingly critical role in enhancing model performan…

cs.CV2026

Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models

Junyan Lin, Junlong Tong, Hao Wu +4

Multimodal Large Language Models (MLLMs) have achieved strong performance across many tasks, yet most systems remain limited to offline inference, requiring complete inputs before…

eess.IV2024

Sparse Focus Network for Multi-Source Remote Sensing Data Classification

Xuepeng Jin, Junyan Lin, Feng Gao +2

Multi-source remote sensing data classification has emerged as a prominent research topic with the advancement of various sensors. Existing multi-source data classification methods…